INDEX

Explanations

phrases indicating movement or transition from one place or state to another

oai_token-act-pair · gpt-3.5-turbo

references to transitional phrases or concepts involving moving from one thing to another

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

humans

-0.63

ª

-0.63

ships

-0.61

ARS

-0.61

ourt

-0.60

Sik

-0.60

Ŀ

-0.59

 Derby

-0.59

cars

-0.59

Shy

-0.59

POSITIVE LOGITS

worldly

0.88

dayName

0.82

 equally

0.79

 versa

0.78

etheless

0.78

 baseman

0.75

 lobe

0.75

resso

0.73

sylv

0.71

agogue

0.71

Activations Density 0.070%

phrases indicating movement or transition from one place or state to another

references to transitional phrases or concepts involving moving from one thing to another

No Comments

No Known Activations